Related papers: SimPose: Effectively Learning DensePose and Surfac…

Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…

Deep learning-based object reconstruction algorithms have shown remarkable improvements over classical methods. However, supervised learning based methods perform poorly when the training data and the test data have different distributions.…

In recent years, policy learning methods using either reinforcement or imitation have made significant progress. However, both techniques still suffer from being computationally expensive and requiring large amounts of training data. This…

We propose a new semi-supervised learning design for human pose estimation that revisits the popular dual-student framework and enhances it two ways. First, we introduce a denoising scheme to generate reliable pseudo-heatmaps as targets for…

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the…

Image normalization is a building block in medical image analysis. Conventional approaches are customarily utilized on a per-dataset basis. This strategy, however, prevents the current normalization algorithms from fully exploiting the…

Humans can easily deduce the relative pose of a previously unseen object, without labeling or training, given only a single query-reference image pair. This is arguably achieved by incorporating i) 3D/2.5D shape perception from a single…

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent…

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based…

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data. To work well in the real world, the policy needs to see many instances of…

Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. For this…

With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3D registration, we propose deep learning-based methods that are trained to find the 3D position of…

The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a…

We consider the problem of source-free unsupervised category-level pose estimation from only RGB images to a target domain without any access to source domain data or 3D annotations during adaptation. Collecting and annotating real-world 3D…

One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of…

Mixture models are well-established learning approaches that, in computer vision, have mostly been applied to inverse or ill-defined problems. However, they are general-purpose divide-and-conquer techniques, splitting the input space into…

One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a method to infer voxel-level transformation from…

Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…

Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that…

Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or computational constraints. To address this limitation, we…